初始化项目，由ModelHub XC社区提供模型

Model: desh2806/shifted_persona_0
Source: Original Platform

.gitattributes

@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+model_name: shifted_model_persona_0_v2
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for shifted_model_persona_0_v2
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.1
+- Transformers: 4.57.6
+- Pytorch: 2.10.0
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-1500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: uniform_prior
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:uniform_prior
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "uniform_prior",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6b0819aa0a4c3db61adae4746f7a7ebe9976be9eee758b4b9467e071bdfb70
+size 5917192

checkpoint-1500/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f9e1ba1049048f2c41bbf78a1cba240c616a8ee1e339177cdbcde522b655d2
+size 11919947

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204d4967f720cb22bb9b669aec4763d5907d9ed6f1969936f3dc43e7a283fea8
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccfffb2e4aef68a5c5dcd5e9f9d26ce56a7e2e8b8cf957932f5509240c05e84
+size 1465

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-1500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bbe284e74298a5b6715dcfd6da1001ad5655a8cf82df3bc6cc3e49cf903165
+size 6289

checkpoint-2250/README.md

@@ -0,0 +1,209 @@
+---
+base_model: uniform_prior
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:uniform_prior
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-2250/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "uniform_prior",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d33f959a9aab57854e5e3b9b530c6e5015845fffe256c6cdc7b3f16da01b3d6
+size 5917192

checkpoint-2250/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-2250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbabb033a07696632334676814a8c1c795c43d5703ce1ad927e2b6f3f0af7f7
+size 11919947

checkpoint-2250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555a5d6c71dd7f0697302d00030ba0bc5cf10873d94f3e399b9b55385002dd8a
+size 14645

checkpoint-2250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7546c248ae2cf40822515d58985c2e3376d31dc6a238d99a434d24ac94723637
+size 1465

checkpoint-2250/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-2250/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-2250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bbe284e74298a5b6715dcfd6da1001ad5655a8cf82df3bc6cc3e49cf903165
+size 6289

checkpoint-3000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: uniform_prior
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:uniform_prior
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-3000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "uniform_prior",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ac7cf92612436ea30df6c7c564c94da8aa1559a9ec30dc966ed168b1af4f89
+size 5917192

checkpoint-3000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5fb2b2a03efc5571804ef3dc85d491f74add9b8b74934ab9baf26167975e65
+size 11919947

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b85a62e621d0543c40339fde04a188ce239066c4a59f48a3512f6fcb94defb
+size 14645

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf66d403a29c8c0be703e5f9e87d5057ff1c237a4dd78b279f5ec32b1037482
+size 1465

checkpoint-3000/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-3000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bbe284e74298a5b6715dcfd6da1001ad5655a8cf82df3bc6cc3e49cf903165
+size 6289

checkpoint-3750/README.md

@@ -0,0 +1,209 @@
+---
+base_model: uniform_prior
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:uniform_prior
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-3750/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "uniform_prior",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedc4138b00fbed43203720715e219ae770603f0c106bc7ec4b039a97b925398
+size 5917192

checkpoint-3750/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-3750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163edb49aca7acbfaf89877f980ad922df26e5cd166d84b0c8c03ad371de0345
+size 11919947

checkpoint-3750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0680e4f67552154bc0b698c56b729bb2994af47dad6925373d7ba2398a9cbd
+size 14645

checkpoint-3750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c5185da1445c3fd6f9fb1a196112b0693198df8b7959c4e0e72cd393356e90
+size 1465

checkpoint-3750/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3750/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-3750/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-3750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bbe284e74298a5b6715dcfd6da1001ad5655a8cf82df3bc6cc3e49cf903165
+size 6289

checkpoint-750/README.md

@@ -0,0 +1,209 @@
+---
+base_model: uniform_prior
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:uniform_prior
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-750/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "uniform_prior",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18af3258f246e9c80b98c0b915f7659ee32e4724ac34cdce625d165dc24caf8c
+size 5917192

checkpoint-750/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501396e39b788a9bcb921e6c7af969e6c074f4005c92a58352b619c2572358ae
+size 11919947

checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe225a4c13bdb5d39388d4ca9f0f2899b5a906b5faef70c66c82410713adcd77
+size 14645

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58df5e87f46732ded49bc1cf3a21b26cffae41caf82dabd88e2d39684618162b
+size 1465

checkpoint-750/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-750/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-750/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-750/trainer_state.json

@@ -0,0 +1,784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7908701181411744,
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.1777843236923218,
+      "learning_rate": 0.00019952000000000001,
+      "loss": 1.8912,
+      "mean_token_accuracy": 0.5405127346515656,
+      "num_tokens": 14665.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.757728385925293,
+      "epoch": 0.02666666666666667,
+      "grad_norm": 0.9262706637382507,
+      "learning_rate": 0.00019898666666666668,
+      "loss": 1.7762,
+      "mean_token_accuracy": 0.5599964261054993,
+      "num_tokens": 29061.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.705195951461792,
+      "epoch": 0.04,
+      "grad_norm": 0.8576209545135498,
+      "learning_rate": 0.00019845333333333334,
+      "loss": 1.7582,
+      "mean_token_accuracy": 0.5612735390663147,
+      "num_tokens": 43628.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.764819598197937,
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.9937595725059509,
+      "learning_rate": 0.00019792000000000003,
+      "loss": 1.7875,
+      "mean_token_accuracy": 0.5601426303386688,
+      "num_tokens": 57878.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.692608082294464,
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.8142558932304382,
+      "learning_rate": 0.00019738666666666667,
+      "loss": 1.7188,
+      "mean_token_accuracy": 0.5711204051971436,
+      "num_tokens": 72081.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.713820493221283,
+      "epoch": 0.08,
+      "grad_norm": 0.8134881854057312,
+      "learning_rate": 0.00019685333333333333,
+      "loss": 1.7262,
+      "mean_token_accuracy": 0.5672860145568848,
+      "num_tokens": 86547.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.7069548845291138,
+      "epoch": 0.09333333333333334,
+      "grad_norm": 0.7980002760887146,
+      "learning_rate": 0.00019632000000000002,
+      "loss": 1.7412,
+      "mean_token_accuracy": 0.5662308156490325,
+      "num_tokens": 100695.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.7331032037734986,
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.8221873044967651,
+      "learning_rate": 0.00019578666666666668,
+      "loss": 1.7445,
+      "mean_token_accuracy": 0.5610231578350067,
+      "num_tokens": 114813.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.7180450558662415,
+      "epoch": 0.12,
+      "grad_norm": 0.8718360662460327,
+      "learning_rate": 0.00019525333333333334,
+      "loss": 1.7297,
+      "mean_token_accuracy": 0.5656625151634216,
+      "num_tokens": 128864.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.6863915205001831,
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7490881085395813,
+      "learning_rate": 0.00019472,
+      "loss": 1.7097,
+      "mean_token_accuracy": 0.5710519969463348,
+      "num_tokens": 143400.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.656905508041382,
+      "epoch": 0.14666666666666667,
+      "grad_norm": 0.7690205574035645,
+      "learning_rate": 0.00019418666666666667,
+      "loss": 1.6377,
+      "mean_token_accuracy": 0.5826482594013214,
+      "num_tokens": 157812.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.70476393699646,
+      "epoch": 0.16,
+      "grad_norm": 0.7643902897834778,
+      "learning_rate": 0.00019365333333333336,
+      "loss": 1.7258,
+      "mean_token_accuracy": 0.5608070731163025,
+      "num_tokens": 171892.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.6601023912429809,
+      "epoch": 0.17333333333333334,
+      "grad_norm": 0.8293864130973816,
+      "learning_rate": 0.00019312000000000002,
+      "loss": 1.6714,
+      "mean_token_accuracy": 0.5756373822689056,
+      "num_tokens": 186019.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.6955374836921693,
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.8544629812240601,
+      "learning_rate": 0.00019258666666666668,
+      "loss": 1.6904,
+      "mean_token_accuracy": 0.5779714524745941,
+      "num_tokens": 200048.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.672298264503479,
+      "epoch": 0.2,
+      "grad_norm": 0.7459447383880615,
+      "learning_rate": 0.00019205333333333335,
+      "loss": 1.6373,
+      "mean_token_accuracy": 0.5774146437644958,
+      "num_tokens": 214845.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.621527373790741,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.778339684009552,
+      "learning_rate": 0.00019152,
+      "loss": 1.6564,
+      "mean_token_accuracy": 0.5799753427505493,
+      "num_tokens": 228965.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.6854836463928222,
+      "epoch": 0.22666666666666666,
+      "grad_norm": 0.7781394720077515,
+      "learning_rate": 0.00019098666666666667,
+      "loss": 1.6731,
+      "mean_token_accuracy": 0.5745640277862549,
+      "num_tokens": 243138.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.648065435886383,
+      "epoch": 0.24,
+      "grad_norm": 0.7444502711296082,
+      "learning_rate": 0.00019045333333333336,
+      "loss": 1.6556,
+      "mean_token_accuracy": 0.5753928661346436,
+      "num_tokens": 257706.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.6733452081680298,
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.6875325441360474,
+      "learning_rate": 0.00018992,
+      "loss": 1.6905,
+      "mean_token_accuracy": 0.5732767701148986,
+      "num_tokens": 271550.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.675937283039093,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.7303425073623657,
+      "learning_rate": 0.00018938666666666666,
+      "loss": 1.6684,
+      "mean_token_accuracy": 0.5771281003952027,
+      "num_tokens": 285690.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.6358152866363525,
+      "epoch": 0.28,
+      "grad_norm": 0.7411030530929565,
+      "learning_rate": 0.00018885333333333335,
+      "loss": 1.6339,
+      "mean_token_accuracy": 0.5838043510913848,
+      "num_tokens": 300104.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.6545907258987427,
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.7895593047142029,
+      "learning_rate": 0.00018832,
+      "loss": 1.6858,
+      "mean_token_accuracy": 0.5718037188053131,
+      "num_tokens": 314047.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.6488535761833192,
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.7785155177116394,
+      "learning_rate": 0.00018778666666666668,
+      "loss": 1.6694,
+      "mean_token_accuracy": 0.5763668715953827,
+      "num_tokens": 328674.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.6801724672317504,
+      "epoch": 0.32,
+      "grad_norm": 0.697731614112854,
+      "learning_rate": 0.00018725333333333334,
+      "loss": 1.6564,
+      "mean_token_accuracy": 0.5734941899776459,
+      "num_tokens": 342932.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.6780007004737854,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.7615799903869629,
+      "learning_rate": 0.00018672,
+      "loss": 1.694,
+      "mean_token_accuracy": 0.5711317896842957,
+      "num_tokens": 357167.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.6752456307411194,
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.715129017829895,
+      "learning_rate": 0.00018618666666666666,
+      "loss": 1.6726,
+      "mean_token_accuracy": 0.5754297077655792,
+      "num_tokens": 371293.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.6538572311401367,
+      "epoch": 0.36,
+      "grad_norm": 0.8093023896217346,
+      "learning_rate": 0.00018565333333333335,
+      "loss": 1.6722,
+      "mean_token_accuracy": 0.5708646178245544,
+      "num_tokens": 385455.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.6819413661956788,
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.7279489636421204,
+      "learning_rate": 0.00018512000000000002,
+      "loss": 1.6482,
+      "mean_token_accuracy": 0.5810510337352752,
+      "num_tokens": 399994.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.6535839796066285,
+      "epoch": 0.38666666666666666,
+      "grad_norm": 0.7264725565910339,
+      "learning_rate": 0.00018458666666666668,
+      "loss": 1.6601,
+      "mean_token_accuracy": 0.5782212734222412,
+      "num_tokens": 414302.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.6291370630264281,
+      "epoch": 0.4,
+      "grad_norm": 0.7391830682754517,
+      "learning_rate": 0.00018405333333333334,
+      "loss": 1.6252,
+      "mean_token_accuracy": 0.5810718059539794,
+      "num_tokens": 428367.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.6454604744911194,
+      "epoch": 0.41333333333333333,
+      "grad_norm": 0.7421492338180542,
+      "learning_rate": 0.00018352,
+      "loss": 1.6548,
+      "mean_token_accuracy": 0.5764368116855622,
+      "num_tokens": 442350.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.6191022634506225,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.6302896738052368,
+      "learning_rate": 0.0001829866666666667,
+      "loss": 1.6362,
+      "mean_token_accuracy": 0.5786097645759583,
+      "num_tokens": 456414.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.694426167011261,
+      "epoch": 0.44,
+      "grad_norm": 0.7121474742889404,
+      "learning_rate": 0.00018245333333333333,
+      "loss": 1.7126,
+      "mean_token_accuracy": 0.5670216321945191,
+      "num_tokens": 470836.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.724251127243042,
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.6601665019989014,
+      "learning_rate": 0.00018192,
+      "loss": 1.7136,
+      "mean_token_accuracy": 0.5723266065120697,
+      "num_tokens": 485043.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.6735360264778136,
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.8272239565849304,
+      "learning_rate": 0.00018138666666666668,
+      "loss": 1.6753,
+      "mean_token_accuracy": 0.5723617672920227,
+      "num_tokens": 499183.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.6469814419746398,
+      "epoch": 0.48,
+      "grad_norm": 0.7188411951065063,
+      "learning_rate": 0.00018085333333333335,
+      "loss": 1.6475,
+      "mean_token_accuracy": 0.5769975543022156,
+      "num_tokens": 513579.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.6747308850288392,
+      "epoch": 0.49333333333333335,
+      "grad_norm": 0.7487552762031555,
+      "learning_rate": 0.00018032,
+      "loss": 1.6823,
+      "mean_token_accuracy": 0.5752046227455139,
+      "num_tokens": 527660.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.666330885887146,
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.6975488662719727,
+      "learning_rate": 0.00017978666666666667,
+      "loss": 1.6582,
+      "mean_token_accuracy": 0.5811319828033448,
+      "num_tokens": 542081.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.6803588151931763,
+      "epoch": 0.52,
+      "grad_norm": 0.737691342830658,
+      "learning_rate": 0.00017925333333333333,
+      "loss": 1.6788,
+      "mean_token_accuracy": 0.5737549722194671,
+      "num_tokens": 556595.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.6843163609504699,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.739733099937439,
+      "learning_rate": 0.00017872,
+      "loss": 1.6939,
+      "mean_token_accuracy": 0.5709910333156586,
+      "num_tokens": 570777.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.6645950436592103,
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.7805267572402954,
+      "learning_rate": 0.00017818666666666669,
+      "loss": 1.6813,
+      "mean_token_accuracy": 0.5687461018562316,
+      "num_tokens": 585138.0,
+      "step": 410
+    },
+    {
+      "entropy": 1.6936459064483642,
+      "epoch": 0.56,
+      "grad_norm": 0.726749062538147,
+      "learning_rate": 0.00017765333333333335,
+      "loss": 1.6973,
+      "mean_token_accuracy": 0.5707198500633239,
+      "num_tokens": 599933.0,
+      "step": 420
+    },
+    {
+      "entropy": 1.6732940793037414,
+      "epoch": 0.5733333333333334,
+      "grad_norm": 0.6750204563140869,
+      "learning_rate": 0.00017712,
+      "loss": 1.6797,
+      "mean_token_accuracy": 0.5727494537830353,
+      "num_tokens": 614132.0,
+      "step": 430
+    },
+    {
+      "entropy": 1.6580298662185669,
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.719950795173645,
+      "learning_rate": 0.00017658666666666667,
+      "loss": 1.6577,
+      "mean_token_accuracy": 0.5744940221309662,
+      "num_tokens": 628571.0,
+      "step": 440
+    },
+    {
+      "entropy": 1.652840507030487,
+      "epoch": 0.6,
+      "grad_norm": 0.6199878454208374,
+      "learning_rate": 0.00017605333333333334,
+      "loss": 1.6518,
+      "mean_token_accuracy": 0.5756324470043183,
+      "num_tokens": 643076.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.6695269465446472,
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.7818489074707031,
+      "learning_rate": 0.00017552000000000003,
+      "loss": 1.6768,
+      "mean_token_accuracy": 0.5710194766521454,
+      "num_tokens": 656943.0,
+      "step": 460
+    },
+    {
+      "entropy": 1.668250596523285,
+      "epoch": 0.6266666666666667,
+      "grad_norm": 0.6790580749511719,
+      "learning_rate": 0.0001749866666666667,
+      "loss": 1.6783,
+      "mean_token_accuracy": 0.5728156328201294,
+      "num_tokens": 671345.0,
+      "step": 470
+    },
+    {
+      "entropy": 1.6558388233184815,
+      "epoch": 0.64,
+      "grad_norm": 0.7647916078567505,
+      "learning_rate": 0.00017445333333333333,
+      "loss": 1.6723,
+      "mean_token_accuracy": 0.5740255832672119,
+      "num_tokens": 685563.0,
+      "step": 480
+    },
+    {
+      "entropy": 1.6663503646850586,
+      "epoch": 0.6533333333333333,
+      "grad_norm": 0.6828808188438416,
+      "learning_rate": 0.00017392000000000002,
+      "loss": 1.6718,
+      "mean_token_accuracy": 0.5754141092300415,
+      "num_tokens": 699746.0,
+      "step": 490
+    },
+    {
+      "entropy": 1.6640026688575744,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7021526098251343,
+      "learning_rate": 0.00017338666666666668,
+      "loss": 1.6442,
+      "mean_token_accuracy": 0.5807092905044555,
+      "num_tokens": 714501.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.6755484104156495,
+      "epoch": 0.68,
+      "grad_norm": 0.6762555241584778,
+      "learning_rate": 0.00017285333333333334,
+      "loss": 1.6864,
+      "mean_token_accuracy": 0.5786374986171723,
+      "num_tokens": 728741.0,
+      "step": 510
+    },
+    {
+      "entropy": 1.6181371688842774,
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.7460752129554749,
+      "learning_rate": 0.00017232,
+      "loss": 1.6443,
+      "mean_token_accuracy": 0.5760051727294921,
+      "num_tokens": 742943.0,
+      "step": 520
+    },
+    {
+      "entropy": 1.6662646651268005,
+      "epoch": 0.7066666666666667,
+      "grad_norm": 0.6818891167640686,
+      "learning_rate": 0.00017178666666666667,
+      "loss": 1.6626,
+      "mean_token_accuracy": 0.5765082776546478,
+      "num_tokens": 757701.0,
+      "step": 530
+    },
+    {
+      "entropy": 1.640554964542389,
+      "epoch": 0.72,
+      "grad_norm": 0.699113130569458,
+      "learning_rate": 0.00017125333333333333,
+      "loss": 1.6219,
+      "mean_token_accuracy": 0.5862498044967651,
+      "num_tokens": 772062.0,
+      "step": 540
+    },
+    {
+      "entropy": 1.692064070701599,
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.7120975852012634,
+      "learning_rate": 0.00017072000000000002,
+      "loss": 1.6991,
+      "mean_token_accuracy": 0.5677917718887329,
+      "num_tokens": 786707.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.6766908407211303,
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.7205502390861511,
+      "learning_rate": 0.00017018666666666668,
+      "loss": 1.6758,
+      "mean_token_accuracy": 0.5790870308876037,
+      "num_tokens": 801236.0,
+      "step": 560
+    },
+    {
+      "entropy": 1.632925820350647,
+      "epoch": 0.76,
+      "grad_norm": 0.738036572933197,
+      "learning_rate": 0.00016965333333333332,
+      "loss": 1.6494,
+      "mean_token_accuracy": 0.5808292210102082,
+      "num_tokens": 815883.0,
+      "step": 570
+    },
+    {
+      "entropy": 1.669986116886139,
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.6785821914672852,
+      "learning_rate": 0.00016912,
+      "loss": 1.6544,
+      "mean_token_accuracy": 0.5800759375095368,
+      "num_tokens": 829570.0,
+      "step": 580
+    },
+    {
+      "entropy": 1.6363327860832215,
+      "epoch": 0.7866666666666666,
+      "grad_norm": 0.6850758790969849,
+      "learning_rate": 0.00016858666666666667,
+      "loss": 1.6549,
+      "mean_token_accuracy": 0.578828877210617,
+      "num_tokens": 844009.0,
+      "step": 590
+    },
+    {
+      "entropy": 1.64016250371933,
+      "epoch": 0.8,
+      "grad_norm": 0.6750107407569885,
+      "learning_rate": 0.00016805333333333336,
+      "loss": 1.6566,
+      "mean_token_accuracy": 0.575623071193695,
+      "num_tokens": 858282.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.6842385530471802,
+      "epoch": 0.8133333333333334,
+      "grad_norm": 0.7148203253746033,
+      "learning_rate": 0.00016752000000000002,
+      "loss": 1.6909,
+      "mean_token_accuracy": 0.5759712219238281,
+      "num_tokens": 872855.0,
+      "step": 610
+    },
+    {
+      "entropy": 1.6071362018585205,
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.709815263748169,
+      "learning_rate": 0.00016698666666666666,
+      "loss": 1.6062,
+      "mean_token_accuracy": 0.5838622927665711,
+      "num_tokens": 887139.0,
+      "step": 620
+    },
+    {
+      "entropy": 1.647024357318878,
+      "epoch": 0.84,
+      "grad_norm": 0.7029419541358948,
+      "learning_rate": 0.00016645333333333335,
+      "loss": 1.6712,
+      "mean_token_accuracy": 0.5723545610904693,
+      "num_tokens": 901212.0,
+      "step": 630
+    },
+    {
+      "entropy": 1.6637583255767823,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.7077947854995728,
+      "learning_rate": 0.00016592,
+      "loss": 1.6467,
+      "mean_token_accuracy": 0.5752432465553283,
+      "num_tokens": 915566.0,
+      "step": 640
+    },
+    {
+      "entropy": 1.6351732969284059,
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.7223191857337952,
+      "learning_rate": 0.00016538666666666667,
+      "loss": 1.6326,
+      "mean_token_accuracy": 0.5809595823287964,
+      "num_tokens": 930155.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.625480556488037,
+      "epoch": 0.88,
+      "grad_norm": 0.6872687339782715,
+      "learning_rate": 0.00016485333333333334,
+      "loss": 1.6096,
+      "mean_token_accuracy": 0.5873603641986846,
+      "num_tokens": 943961.0,
+      "step": 660
+    },
+    {
+      "entropy": 1.6413599967956543,
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.6594866514205933,
+      "learning_rate": 0.00016432,
+      "loss": 1.692,
+      "mean_token_accuracy": 0.5740860402584076,
+      "num_tokens": 958370.0,
+      "step": 670
+    },
+    {
+      "entropy": 1.6765796422958374,
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.6635148525238037,
+      "learning_rate": 0.00016378666666666666,
+      "loss": 1.6493,
+      "mean_token_accuracy": 0.5794400811195374,
+      "num_tokens": 972746.0,
+      "step": 680
+    },
+    {
+      "entropy": 1.64844651222229,
+      "epoch": 0.92,
+      "grad_norm": 0.6969758868217468,
+      "learning_rate": 0.00016325333333333335,
+      "loss": 1.6465,
+      "mean_token_accuracy": 0.5806655645370483,
+      "num_tokens": 987210.0,
+      "step": 690
+    },
+    {
+      "entropy": 1.628549289703369,
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.6831814050674438,
+      "learning_rate": 0.00016272000000000001,
+      "loss": 1.6445,
+      "mean_token_accuracy": 0.5774340748786926,
+      "num_tokens": 1001627.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.6590662002563477,
+      "epoch": 0.9466666666666667,
+      "grad_norm": 0.7329531908035278,
+      "learning_rate": 0.00016218666666666668,
+      "loss": 1.6746,
+      "mean_token_accuracy": 0.5709875702857972,
+      "num_tokens": 1015828.0,
+      "step": 710
+    },
+    {
+      "entropy": 1.6233970403671265,
+      "epoch": 0.96,
+      "grad_norm": 0.6673484444618225,
+      "learning_rate": 0.00016165333333333334,
+      "loss": 1.6213,
+      "mean_token_accuracy": 0.5806674182415008,
+      "num_tokens": 1030323.0,
+      "step": 720
+    },
+    {
+      "entropy": 1.6572086334228515,
+      "epoch": 0.9733333333333334,
+      "grad_norm": 0.7702727913856506,
+      "learning_rate": 0.00016112,
+      "loss": 1.6664,
+      "mean_token_accuracy": 0.5798572361469269,
+      "num_tokens": 1044685.0,
+      "step": 730
+    },
+    {
+      "entropy": 1.620801281929016,
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.6698365211486816,
+      "learning_rate": 0.0001605866666666667,
+      "loss": 1.6032,
+      "mean_token_accuracy": 0.5835649371147156,
+      "num_tokens": 1058992.0,
+      "step": 740
+    },
+    {
+      "entropy": 1.6149493217468263,
+      "epoch": 1.0,
+      "grad_norm": 0.6890732645988464,
+      "learning_rate": 0.00016005333333333335,
+      "loss": 1.6306,
+      "mean_token_accuracy": 0.5798977136611938,
+      "num_tokens": 1073437.0,
+      "step": 750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 727173730437120.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bbe284e74298a5b6715dcfd6da1001ad5655a8cf82df3bc6cc3e49cf903165
+size 6289

config.json

@@ -0,0 +1,54 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 1,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "transformers_version": "4.57.6",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1
+  ],
+  "pad_token_id": 1,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75e3f2e643e7f3798802a0b143c9d835a2d59a97b17b600f19da6f8fa858c26
+size 536223056

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074